xinntao / realesrgan

Practical Image Restoration Algorithms for General/Anime Images

  • Public
  • 5.8M runs
  • GitHub
  • Paper
  • License

Input

Output

Run time and cost

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 5 seconds.

Readme

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

If Real-ESRGAN is helpful, please help to ⭐ the Github Repo and recommend it to your friends 😊

Model Descriptions

Option Weight Name Description
▶General - RealESRGANplus: <RealESRGAN_x4plus.pth> A large model for general images
▶General - v3: <realesr-general-x4v3.pth> A tiny model for general images
▶Anime - anime6B: <RealESRGAN_x4plus_anime_6B.pth> A large model for anime images/illustrations
▶AnimeVideo - v3: <realesr-animevideov3.pth> A tiny model for anime images, especially for anime videos

download GitHub Stars arXiv

📧Contact

If you have any question, please email xintao.wang@outlook.com or xintaowang@tencent.com.